Drone-based 3D Reconstruction of Plants in Field Conditions Using Neural Radiance Fields (NeRFs)

Shambhavi Joshi, Ashlyn Rairdin, Elizabeth Tranel, Talukder Zaki Jubery, Soumik Sarkar, ARTI SINGH, Baskar Ganapathysubramanian, Adarsh Krishnamurthy

Keywords: Neural Radiance Fields, 3D plant reconstruction, Drone phenotyping, Multi-device comparison

TL;DR: Drone imagery is an effective way to capture field plots for 3D reconstruction. Its consistent coverage and stable viewpoints make it the most reliable option among the devices tested.

Abstract:

The performance of 3D reconstruction using Neural Radiance Fields (NeRFs) for outdoor phenotyping of plants is strongly influenced by the imaging modality used for data collection. We compare drone, handheld, and 360° ground robot datasets collected over soybean and mungbean plots, and evaluate reconstruction quality using 2D metrics PSNR, SSIM, LPIPS, and 3D geometric metrics precision, recall, and F1 score.
Drone imagery produced the highest geometric fidelity, handheld captures achieved the strongest 2D appearance quality, and the 360° captures lagged in both metrics due to spherical distortion and motion artifacts. The consistency of the drone-based reconstructions highlights its suitability for field-scale 3D modeling and positions it as a practical foundation for future phenotyping applications.

Submission Number: 19